Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Codex starts encrypting sub-agent prompts

github.com

Post reply on HN
Print view View original

141–150 of 272 posts

Re: Codex starts encrypting sub-agent prompts

#141

Post by Jean-Papoulos »

themgt wrote: post #128
niam wrote: post #34

This title is easy to misinterpret. If I understand correctly: Codex now encrypts sub-agent prompts and hides those prompts from the user. edit: originally was "Codex starts encrypting prompts, uses cyphertext for inference instead"

It's sort of insane though, you not only have dozens/hundreds of stochastic agents running on your machine, but you cannot even inspect the instructions those agents are working off of? I've gone in to look at Claude subagent/workflows and sometimes been like "no this was a mistake to spin up" ... Codex users just get to token yolo the encrypted telephone operator instructions+shell from orchestrator to subagents?

You already have an agent freely doing stuff on your machine. Subagents prompts are a weird place to draw a line. It's not like you're reading everything the agent is doing in any case, let's not kid ourselves.

Re: Codex starts encrypting sub-agent prompts

#142

Post by oblio »

agumonkey wrote: post #116
hnlmorg wrote: post #104

Earlier quoted context omitted.

I don’t disagree with your divinity spell comparison but unfortunately there is a lot of value in the prompts because these spells are the “programming languages” of LLMs.

yeah i get it too, i'm just flabbergasted that this is today's market it reminds me of the pre-vulkan game programming days.. drivers were black boxes, game developpers had to resort to magic tricks to do stuff, until everybody got fed up and wanted some logical ground to operate

Further proof that this tech stack is immature and would have needed to bake for a more years.

In an ideal world this would have been public tech like ARPANET or WWW and there would have been 2-3 major iterations (until the equivalent of Claude 7-8) and only then would everyone have tried to build huge businesses on top of it.

I mean, sure, it's sort of usable, but the churn is insane. And we're burning the planet (and probably the economy, too) for it.

Re: Codex starts encrypting sub-agent prompts

#143

Post by tpurves »

hansihe wrote: post #117
niam wrote: post #34

This title is easy to misinterpret. If I understand correctly: Codex now encrypts sub-agent prompts and hides those prompts from the user. edit: originally was "Codex starts encrypting prompts, uses cyphertext for inference instead"

It seems likely to me this was driven by the `ultra` mode in 5.6, which fans subagents to do work. This mode was previously only available in the web UI (what was previously known as pro?) It seems possible they trained this by doing full RL rollouts of agents interacting with each other. They likely view these prompts somewhat the same as raw reasoning traces, they don't want people to train directly on them. I am u…

"Latent space representation" I have been waiting for this moment in the evolution of AI. Well, waiting with some trepidation. It seems inevitable that frontier AI's will, at some point, leave behind human-comprehensible representations of language. Purely for functional reasons, it's going to start making sense for AI agents to communicate amongst themselves in much more efficient ways than borrowing the languages of flesh-bag humans as an interface medium.

I Imagine next that programming languages, interfaces and API design starts going this direction next. Being written, expressed and optimized as blobs of high dimensional vector space. As humans we might still be able to understand some abstractions of what our AI's are talking about to each other, but maybe not more so then we understand how different regions of our own brain communicate with each other.

Re: Codex starts encrypting sub-agent prompts

#144

Post by oblio »

anon373839 wrote: post #135
hyperbovine wrote: post #124

Earlier quoted context omitted.

Feels strongly like we're in the late-stage-AI-unicorn phase. If this is really their moat then the Chinese companies will win.

This and the overly stylized model names. Mythos? Sol? Please, it's another version bump.

Anthropic at least is consistent in their naming. They're all literary genres, ever bigger ones.

Re: Codex starts encrypting sub-agent prompts

#145

Post by djeastm »

themgt wrote: post #128
niam wrote: post #34

This title is easy to misinterpret. If I understand correctly: Codex now encrypts sub-agent prompts and hides those prompts from the user. edit: originally was "Codex starts encrypting prompts, uses cyphertext for inference instead"

It's sort of insane though, you not only have dozens/hundreds of stochastic agents running on your machine, but you cannot even inspect the instructions those agents are working off of? I've gone in to look at Claude subagent/workflows and sometimes been like "no this was a mistake to spin up" ... Codex users just get to token yolo the encrypted telephone operator instructions+shell from orchestrator to subagents?

>but you cannot even inspect the instructions those agents are working off of?

It makes more sense when you realize they don't want developers to be doing any coding at all. That's what they seem to be moving towards. From product manager to product via AI.

Re: Codex starts encrypting sub-agent prompts

#146

Post by minraws »

skeledrew wrote: post #118
minraws wrote: post #25

Earlier quoted context omitted.

ooooooof yeah totally misinterpreted it lmao

Given what we know about the company, I find it crazy anyone would misinterpret along those lines lol.

I can only say I am a little too optimistic about the technology world in general. Or at least would love to see some good news once in a while given the state of the world.

Re: Codex starts encrypting sub-agent prompts

#147

Post by afzalive »

iknownothow wrote: post #42
embedding-shape wrote: post #30

Earlier quoted context omitted.

Sure. "Traditionally", your agent would send a text prompt to the sub-agent, then it goes off doing it's work. In the logs/session data, the clear-text prompt would be there, so if I want to see what's happening, I just browse the data. It's all just clear-text prompts being sent everywhere, even when you were using the experimental "sub-agents" stuff in Codex, before Sol et al was available. Now, when using Sol or T…

Gotcha and thank you! So the encryption is happening on the OpenAI backend and the agent's clear-text output designated to the sub-agent never reaches local. Which is a real problem since you can't intercept/monkey patch the ciphertext to decrypt it locally to be able see the clear-text since we don't have the encryption key/algo/salt. No hacking :(

I wonder if you can just ask the model what it means.

Re: Codex starts encrypting sub-agent prompts

#148

Post by canadiantim »

pshirshov wrote: post #22
mapontosevenths wrote: post #7

Earlier quoted context omitted.

Anthropic and Google already charge extra to use your own harness. That's 100% of the reason I'm using OpenAI. If they go down that path I'll just go back to my old buddy Claude, or maybe buy a second Spark and keep it local.

Well, my backup plan is GLM. Cheap and not that bad really.

GLM feels a lot less cheap than the numbers say it is

Re: Codex starts encrypting sub-agent prompts

#150

Post by embedding-shape »

Jean-Papoulos wrote: post #141
themgt wrote: post #128

Earlier quoted context omitted.

It's sort of insane though, you not only have dozens/hundreds of stochastic agents running on your machine, but you cannot even inspect the instructions those agents are working off of? I've gone in to look at Claude subagent/workflows and sometimes been like "no this was a mistake to spin up" ... Codex users just get to token yolo the encrypted telephone operator instructions+shell from orchestrator to subagents?

You already have an agent freely doing stuff on your machine. Subagents prompts are a weird place to draw a line. It's not like you're reading everything the agent is doing in any case, let's not kid ourselves.

When things go wrong I very much read the session traces to figure out what in my prompt wasn't good/explicit enough, then retry to evaluate if it would have helped.

I was about to do the same with Sol + Ultra, but then discovered this encryption issue that prevents me from doing the same for sub-agents.

Post reply on HN